{"id":"W1581639473","doi":"10.1007/s10664-012-9209-9","title":"Automated topic naming","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of British Columbia; University of Alberta","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Topic model; Commit; Categorization; Software; Context (archaeology); Information retrieval; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Data science; Database; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003726395,0.001777037,0.002168254,0.01020294,0.003513765,0.006714604,0.00243726,0.001748197,0.05306211],"category_scores_gemma":[0.01934082,0.001108353,0.002548289,0.005988275,0.0008304082,0.008740413,0.006092536,0.002225122,0.03667612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001755207,"about_ca_system_score_gemma":0.003584174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003249467,"about_ca_topic_score_gemma":0.005071269,"domain_scores_codex":[0.993664,0.001791289,0.0007036392,0.001755041,0.001518303,0.0005676675],"domain_scores_gemma":[0.9850186,0.005110934,0.0006881762,0.004688126,0.003740475,0.0007536874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006562417,0.0001802798,0.004144578,0.0007872213,0.0001544787,0.0002651323,0.001330256,0.001746112,0.03847883,0.03234034,0.1396422,0.7802744],"study_design_scores_gemma":[0.0002735944,0.0002047094,0.00797001,0.0003097302,0.0003707513,0.001523081,0.003259039,0.1944797,0.09141652,0.1349583,0.5649529,0.0002819064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02163064,0.00117821,0.8201336,0.001090958,0.001355815,0.0008249888,0.01518872,0.1113894,0.02720772],"genre_scores_gemma":[0.1610012,0.0006583045,0.7594329,0.0003307637,0.0006044373,0.0007436351,0.03936123,0.009452349,0.0284151],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05306211,"threshold_uncertainty_score":0.1775104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0256654668367926,"score_gpt":0.2953701151461752,"score_spread":0.2697046483093826,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}